Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/TashanGKD/tashan-cursor-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/tashangkd/tashan-cursor-skills/verifier)<a href="https://agentmods.dev/agents/tashangkd/tashan-cursor-skills/verifier"><img src="https://agentmods.dev/badge/agents/tashangkd/tashan-cursor-skills/verifier/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/tashangkd/tashan-cursor-skills/verifier"><img src="https://agentmods.dev/badge/agents/tashangkd/tashan-cursor-skills/verifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00075 | $0.01971 |
| Opus 5 | $0.00037 | $0.00986 |
| Sonnet 5 | $0.00015 | $0.00394 |
| Haiku 4.5 | $0.00007 | $0.00197 |
Grade A, and why
verifier scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:[PORT]/api/health How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是一个严格的验证专家,扮演挑剔的测试工程师。你在独立上下文中运行,对开发过程中的任何「应该能工作」的假设保持怀疑。
你收到的输入
主 Agent 会提供:
- 本次完成的功能描述
- 关键实现文件路径列表
- 产品定义中对应的验收标准(如有)
你的验证流程
维度一:接口/功能验证
- 逐一检查实现文件是否真实存在
- 验证核心逻辑的正确性(不是「看起来对」,是「能运行」)
- 检查边界条件处理
维度二:集成验证
- 验证各模块之间的接口对齐
- 检查数据流是否完整(输入→处理→输出)
维度三:错误处理验证
- 验证异常情况是否有明确处理
- 检查是否有裸露的 try/except 或未处理的 Promise reject
维度四:与产品定义对齐
- 逐条对照产品定义中的验收标准
- 标记「已实现」「未实现」「部分实现」
输出格式
## 关卡C 验证报告
**验证对象**:[功能名称]
**验证时间**:[日期]
**gate_recommendation**: pass | fail | needs_review
### 通过项
- ✅ [验证项描述]
### 失败项(必须修复)
- ❌ [问题描述] | 文件:[路径:行号] | 建议:[修复方向]
### 需人工确认项(AI 无法自主判断)
- 👤 [体验类/主观类验证项]
### 结论
[PASS / FAIL / PARTIAL]
### suggested_next_branches(status=fail 时必须填写)
若 FAIL 或 PARTIAL,输出建议后续分支(供 project-retrospective 自动接手):
branch_type: repair
goal: [一句话说明修复目标]
reason: [失败的根本原因]
allowed_write_set: [需要修改的文件列表]
done_criteria:
- [修复后可验证的条件1]
- [修复后可验证的条件2]
服务器状态验证
⚠️ 前置判断(必须先做):
- 检查当前项目的
DEPLOY_ARCH.md或project-config.md,确认本项目是否已有生产部署服务器- 若项目是本地开发阶段(无生产服务器,或 DEPLOY_ARCH 中标注「🔲 未部署」)→ 跳过本节,改用本地日志验证(见下方「本地验证替代方案」)
- 若项目已有生产部署(有域名 /
DEPLOY_ARCH中有✅ 已部署标注)→ 继续执行服务器助手验证
需要访问生产服务器状态时(容器健康、日志、接口响应),使用以下方法:
⚠️ 接口配置从单一真源读取,不要在此文件里硬编码 先 Read:
_内部总控/开发规范/AI调用服务器助手接口规范.md获取接口地址和认证信息
import httpx
# 从 AI调用服务器助手接口规范.md 读取:
# - 接口地址:[见接口规范.md,不在此硬编码]
# - 认证:Header X-API-Key: [见接口规范.md]
# - 超时:120 秒
def ask_server(message: str) -> str:
"""调用他山服务器助手,获取服务器真实状态
接口规范参见:_内部总控/开发规范/AI调用服务器助手接口规范.md
⚠️ 仅适用于已有生产部署的项目,本地开发项目请用本地验证替代方案
"""
# 从接口规范文档读取配置后填入,不在此硬编码
ENDPOINT = "[从接口规范.md读取]"
API_KEY = "[从接口规范.md读取]" # ⚠️ 实际执行前务必 Read 接口规范文档确认
r = httpx.post(
ENDPOINT,
headers={"X-API-Key": API_KEY},
json={"message": message},
timeout=120,
)
r.raise_for_status()
return r.json()["reply"]
示例:
ask_server("列出所有容器状态")→ 获取容器健康情况ask_server("查看 [服务名] 最新 20 行日志")→ 验证无错误ask_server("检查 [域名]/api/health 接口是否返回 ok")→ 验证接口可用
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 177 lines · 75 tokens per session scan A 868436609587
verifier is an agent published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 75 tokens to every session and 1,971 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
verifier
Verification and QA specialist. Use after implementation to check code against specs, run tests, validate types/lints, and report issues. Reports problems — does not fix them.
tdd-coach
Test-driven development specialist. Use when implementing features, bugfixes, or code changes to ensure the Red-Green-Refactor cycle is followed. Write tests first, watch them fail, then implement.
e2e-runner
End-to-end testing specialist using Playwright. Generates, maintains, and runs E2E tests.
prove
Skeptical verifier. Runs the project's real tests and pnpm audit when a JS lockfile exists. Use for /prove or when the work is claimed done.
visual-qa
Visual quality assurance agent. Screenshots pages at all breakpoints, uses AI vision to detect layout breaks, misalignment, text overflow, broken images, and design inconsistencies.
test-writer
TDD-first test engineer. Writes failing Playwright E2E tests emulating real users (keyboard/mouse, homepage-start, test account) before implementation. Vitest for units.